Fréttir

Erindi á vegum IEEE

11.12.2006

IEEE á Íslandi og Rafmagns- og tölvuverkfræðiskor Verkfræðideildar Háskóla Íslands standa fyrir fræðslufundi þar sem flutt verður erindið: Gagnabræðsla stoðvigravéla til flokkunar á SAR og fjölrása fjarkönnunargögnum. Fyrirlesari verður Björn Waske frá Háskólanum í Bonn. Fundurinn verður í húsakynnum verkfræðideildar Háskóla Íslands, VR-II, stofu 158, miðvikudaginn 13. desember, kl. 16:00.

Ágrip:

Fusion of Support Vector Machines for Classifying SAR and Multispectral Imagery from Agricultural Areas.

Björn Waske, Center for Remote Sensing of Land Surfaces, University of Bonn.

The classification of multisensor data sets, consiting of multitemporal SAR data and optical imagery is addressed. The concept is based on the decision fusion of different outputs. Each data source is treated separately and classified by a support vector machine (SVM). Instead of fusing the final classification outputs ( i.e., land cover classes), the original outputs of each SVM discriminant function are used in the subsequent fusion process. This fusion is performed by another SVM, which is trained on the a priori outputs. In addition two voting schemes are applied to create the final classification results. The results are compared with common parametric and nonparametric classifier methods, i.e., decision trees, maximum likelihood classifier and classifier ensembles. The proposed SVM-based fusion approach outperforms all other approaches and significantly improves the results of a single SVM, which is trained on the whole multisensor data set.

Senda grein